Automated Machine Learning and AI Agent Tools for Clinical Prediction Modelling
Overview
Provides a streamlined workflow for building, validating, and reporting clinical prediction models. Combines standard machine learning tools with an optional AI agent that recommends appropriate statistical methods, runs sensitivity analyses, and flags common pitfalls. Includes automated generation of reports aligned with TRIPOD+AI reporting guidance (Collins et al. (2024 doi:10.1136/bmj-2023-078378)) for reproducible, guideline-aligned research.
- Added calibration plots (binned or smoothed) and Brier score to
tr_validate(), closing a TRIPOD+AI reporting gap. Newcalibration_methodargument ("binned"or"smooth"). - Calibration plot now included in
tr_tripod_report()output. - Added robustness handling for models with limited probability variation (e.g. tree-based models with many identical predictions).
- Added survival analysis support:
tr_fit_survival()(Cox Proportional Hazards and Random Survival Forest via thecensored/aorsfengines) andtr_validate_survival()(concordance index / C-index). - Added
tr_launch_app(): an interactive Shiny application for the full triageR workflow (upload data, fit and compare models, validate, explain, review, and download a TRIPOD+AI report) without writing R code.
Show all changes in 0.2.0Hide the rest of the changes in 0.2.0
- Fixed test suite reliability issues related to lazy-loaded survival datasets.
From NEWS.md in the release
Install
Health
- OK13 OK2026-08-09
- ERROR5 ERROR2026-07-30
Documentation
- Help pages
- 14 (1 internal)includes a package overview page
- Examples that run
- 62%8 run in a plain check (3 of them under a condition) · 5 never run
- Exported functions with examples
- 100%
- Documented parameters
- 99%
- Return-value docs
- 100%
- Help pages citing references
- 0%
Downloads
Repository
Issues over time
9 development-tooling and community-health practices detected across 4 families in the upstream repository
Checks run against github.com/devwebwacky/triager on 2026-10-11.
The R CMD check workflow runs on Linux, macOS and Windows, and on R-devel
GitHub Pages site last deployed 2026-09-05 · The repository has a site deploy workflow
pkgdown site last built 2026-09-05
Dependencies
Installing triageR adds 134 packages (66 with compiled code, 108 MB of source tarballs). Heaviest: stringi 11 MB, ggplot2 6.0 MB, data.table 5.7 MB.
Code & Tests
People & History
Package metadata
- First published
- 2026-07-29
- Total releases
- 3 / 1 yrs
- License
- MIT + file LICENSE OSI
- Minimum R
- ≥ 4.1.0
- Download size
- 263 KB
Cite
Cite this package
Run in R for the authors' preferred citation:
citation("triageR")This package has no citation file, so citation() returns this entry built from DESCRIPTION.
Cite the R Observatory
For a number measured here: a download total, a coverage figure, an archival date.
From data release v2026-10-17, which the citation names so these numbers can be found later. More on citing and the projects behind them.